Gemini BridgeSAFE
A lightweight MCP server bridging AI agents to Google's Gemini AI via official CLI
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A lightweight MCP (Model Context Protocol) server that enables AI coding assistants to interact with Google's Gemini AI through the official CLI. Works with Claude Code, Cursor, VS Code, and other MCP-compatible clients. Designed for simplicity, reliability, and seamless integration.
✨ Features
- Direct Gemini CLI Integration: Zero API costs using official Gemini CLI
- Three MCP Tools: Basic queries, file analysis, and web search capabilities
- Stateless Operation: No sessions, caching, or complex state management
- Production Ready: Robust error handling with configurable 60-second timeouts
- Minimal Dependencies: Only requires
mcp>=2,<3and Gemini CLI - Easy Deployment: Support for both uvx and traditional pip installation
- Universal MCP Compatibility: Works with any MCP-compatible AI coding assistant
- Modern Python: Uses pathlib and modern type hints (Python 3.10+)
🚀 Quick Start
Prerequisites
- Install Gemini CLI:
npm install -g @google/gemini-cli
- Authenticate with Gemini:
gemini auth login
- Verify installation:
gemini --version
Installation
🎯 Recommended: PyPI Installation
# Install from PyPI pip install gemini-bridge # Add to Claude Code with uvx (recommended) claude mcp add gemini-bridge -s user -- uvx gemini-bridge
Alternative: From Source
# Clone the repository git clone https://github.com/shelakh/gemini-bridge.git cd gemini-bridge # Build and install locally u
5c2511dc88b9OBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add gemini-bridge -- uvx gemini-bridge
{
"mcpServers": {
"gemini-bridge": {
"command": "uvx",
"args": [
"gemini-bridge"
]
}
}
}Exposed tools (3)
1 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
consult_gemini | write | Send a query directly to the Gemini CLI. |
consult_gemini_with_files | write | Send a query to the Gemini CLI with file context. |
web_search | read | Ask Gemini queries with web search context. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
5c2511dc88b9full audit observations/trust-audit/mcp-server/elyin__gemini-bridge.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 5c2511dc88b9 | SAFE | B | 89 | first audit |
Questions
What is the Gemini Bridge MCP server?
A lightweight MCP server bridging AI agents to Google's Gemini AI via official CLI
What tools does Gemini Bridge expose?
3 in total: 1 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Gemini Bridge safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Gemini Bridge need?
No credential environment variables were found in its source, so it appears to need none.
How current is this page?
The grade is for one exact copy of the source (5c2511dc88b9), read on 2026-10-07. The repository is watched and re-audited when it changes.